Skip to main content
SpringerLink
Log in

Segmentation of white matter hyperintensities on 18F-FDG PET/CT images with a generative adversarial network

  • Original Article
  • Published:
European Journal of Nuclear Medicine and Molecular Imaging Aims and scope Submit manuscript

Abstract

Purpose

White matter hyperintensities (WMH) are typically segmented using MRI because WMH are hardly visible on 18F-FDG PET/CT. This retrospective study was conducted to segment WMH and estimate their volumes from 18F-FDG PET with a generative adversarial network (WhyperGAN).

Methods

We selected patients whose interval between MRI and FDG PET/CT scans was within 3 months, from January 2017 to December 2018, and classified them into mild, moderate, and severe groups by following the semiquantitative rating method of Fazekas. For each group, 50 patients were selected, and of them, we randomly selected 35 patients for training and 15 for testing. WMH were automatically segmented from FLAIR MRI with manual adjustment. Patches of WMH were extracted from 18F-FDG PET and segmented MRI. WhyperGAN was compared with H-DenseUnet, a deep learning method widely used for segmentation tasks, for segmentation performance based on the dice similarity coefficient (DSC), recall, and average volume differences (AVD). For volume estimation, the predicted WMH volumes from PET were compared with ground truth volumes.

Results

The DSC values were associated with WMH volumes on MRI. For volumes >60 mL, the DSC values were 0.751 for WhyperGAN and 0.564 for H-DenseUnet. For volumes ≤60 mL, the DSC values rapidly decreased as the volume decreased (0.362 for WhyperGAN vs. 0.237 for H-DenseUnet). For recall, WhyperGAN achieved the highest value in the severe group (0.579 for WhyperGAN vs. 0.509 for H-DenseUnet). For AVD, WhyperGAN achieved the lowest score in the severe group (0.494 for WhyperGAN vs. 0.941 for H-DenseUnet). For the WMH volume estimation, WhyperGAN performed better than H-DenseUnet and yielded excellent correlation coefficients (r = 0.998, 0.983, and 0.908 in the severe, moderate, and mild group).

Conclusions

Although limited by visual analysis, the WhyperGAN based can be used to automatically segment and estimate volumes of WMH from 18F-FDG PET/CT. This would increase the usefulness of 18F-FDG PET/CT for the evaluation of WMH in patients with cognitive impairment.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

References

  1. Fiford CM, Manning EN, Bartlett JW, Cash DM, Malone IB, Ridgway GR, et al. White matter hyperintensities are associated with disproportionate progressive hippocampal atrophy. Hippocampus. 2017;27(3):249–62.

    Article  CAS  Google Scholar 

  2. Liu CK, Miller BL, Cummings JL, Mehringer CM, Goldberg MA, Howng SL, et al. A quantitative MRI study of vascular dementia. Neurology. 1992;42(1):138–43.

    Article  CAS  Google Scholar 

  3. Erten-Lyons D, Woltjer R, Kaye J, Mattek N, Dodge HH, Green S, et al. Neuropathologic basis of white matter hyperintensity accumulation with advanced age. Neurology. 2013;81(11):977–83.

    Article  Google Scholar 

  4. Lindemer ER, Greve DN, Fischl B, Augustinack JC, Salat DH. Differential regional distribution of juxtacortical white matter signal abnormalities in aging and Alzheimer’s disease. J Alzheimers Dis. 2017;57(1):293–303.

    Article  Google Scholar 

  5. Brickman AM, Zahodne LB, Guzman VA, Narkhede A, Meier IB, Griffith EY, et al. Reconsidering harbingers of dementia: Progression of parietal lobe white matter hyperintensities predicts Alzheimer's disease incidence. Neurobiol Aging. 2015;36(1):27–32.

    Article  CAS  Google Scholar 

  6. Tosto G, Zimmerman ME, Hamilton JL, Carmichael OT, Brickman AM. Alzheimer's disease neuroimaging I. The effect of white matter hyperintensities on neurodegeneration in mild cognitive impairment. Alzheimers Dement. 2015;11(12):1510–9.

    Article  Google Scholar 

  7. Scheltens P, Barkhof F, Leys D, Pruvo JP, Nauta JJ, Vermersch P, et al. A semiquantative rating scale for the assessment of signal hyperintensities on magnetic resonance imaging. J Neurol Sci. 1993;114(1):7–12.

    Article  CAS  Google Scholar 

  8. Bouter C, Henniges P, Franke TN, Irwin C, Sahlmann CO, Sichler ME, et al. (18)F-FDG-PET detects drastic changes in brain metabolism in the Tg4–42 model of Alzheimer's disease. Front Aging Neurosci. 2018;10:425.

    Article  CAS  Google Scholar 

  9. Foster B, Bagci U, Mansoor A, Xu Z, Mollura DJ. A review on segmentation of positron emission tomography images. Comput Biol Med. 2014;50:76–96.

    Article  Google Scholar 

  10. Yi X, Walia E, Babyn P. Generative adversarial network in medical imaging: a review. Med Image Anal. 2019;58:101552.

    Article  Google Scholar 

  11. Isola P, Zhu J-Y, Zhou T, Efros AA. Image-to-image translation with conditional adversarial networks. arXiv e-prints; 2016. pp. arXiv:1611.07004.

  12. Son J, Park SJ, Jung K-H. Retinal Vessel Segmentation in fundoscopic images with generative adversarial networks. arXiv e-prints; 2017. pp. arXiv:1706.09318.

  13. Huo Y, Xu Z, Bao S, Bermudez C, Plassard AJ, Liu J, et al. Splenomegaly segmentation using global convolutional kernels and conditional generative adversarial networks. Medical Imaging 2018: Image Processing; 2018. pp. 1057409.

  14. Das JRP, Pankajakshan V. Brain tumor segmentation using discriminator loss. 2019 National Conference on Communications (NCC); 2019. pp. 1–6.

  15. Chen L, Shen C, Zhou Z, Maquilan G, Albuquerque K, Folkert MR, et al. Automatic PET cervical tumor segmentation by combining deep learning and anatomic prior. Phys Med Biol. 2019;64(8):085019.

    Article  Google Scholar 

  16. Leung KH, Marashdeh W, Wray R, Ashrafinia S, Pomper MG, Rahmim A, et al. A physics-guided modular deep-learning based automated framework for tumor segmentation in PET. Phys Med Biol. 2020. https://doi.org/10.1088/1361-6560/ab8535.

  17. Blanc-Durand P, Van Der Gucht A, Schaefer N, Itti E, Prior JO. Automatic lesion detection and segmentation of 18F-FET PET in gliomas: A full 3D U-net convolutional neural network study. PLoS One. 2018;13(4):e0195798.

    Article  Google Scholar 

  18. Oh KT, Lee S, Lee H, Yun M, Yoo SK. Semantic segmentation of white matter in FDG-PET using generative adversarial network. J Digit Imaging. 2020. https://doi.org/10.1007/s10278-020-00321-5.

  19. Zhang W, Li R, Deng H, Wang L, Lin W, Ji S, et al. Deep convolutional neural networks for multi-modality isointense infant brain image segmentation. Neuroimage. 2015;108:214–24.

    Article  Google Scholar 

  20. Nie D, Wang L, Gao Y, Shen D. Fully convolutional networks for multi-modality isointense infant brain image segmentation. Proc IEEE Int Symp Biomed Imaging. 2016;2016:1342–5.

    PubMed  PubMed Central  Google Scholar 

  21. Fazekas F, Chawluk JB, Alavi A, Hurtig HI, Zimmerman RA. MR signal abnormalities at 1.5 T in Alzheimer's dementia and normal aging. AJR Am J Roentgenol. 1987;149(2):351–6.

    Article  CAS  Google Scholar 

  22. Nie B, Liu H, Chen K, Jiang X, Shan B. A statistical parametric mapping toolbox used for voxel-wise analysis of FDG-PET images of rat brain. PLoS One. 2014;9(9):e108295.

    Article  Google Scholar 

  23. Tsai JZ, Peng SJ, Chen YW, Wang KW, Li CH, Wang JY, et al. Automated segmentation and quantification of white matter hyperintensities in acute ischemic stroke patients with cerebral infarction. PLoS One. 2014;9(8):e104011.

    Article  Google Scholar 

  24. Dice LR. Measures of the amount of ecologic association between species. Ecology. 1945;26(3):297–302.

    Article  Google Scholar 

  25. Li X, Chen H, Qi X, Dou Q, Fu CW, Heng PA. H-DenseUNet: Hybrid densely connected UNet for liver and tumor segmentation from CT volumes. IEEE Trans Med Imaging. 2018;37(12):2663–74.

    Article  Google Scholar 

  26. Guerrero R, Qin C, Oktay O, Bowles C, Chen L, Joules R, et al. White matter hyperintensity and stroke lesion segmentation and differentiation using convolutional neural networks. NeuroImage: Clin. 2018;17:918–34.

    Article  CAS  Google Scholar 

  27. Prins ND, Scheltens P. White matter hyperintensities, cognitive impairment and dementia: an update. Nat Rev Neurol. 2015;11(3):157–65.

    Article  Google Scholar 

  28. Xu TGY, Bloch I. From neonatal to adult brain MR image segmentation in a few seconds using 3D-like fully convolutional network and transfer learning. 2017 IEEE International Conference on Image Processing (ICIP); 2017. pp. 4417–21.

  29. Andermatt S, Pezold S, Cattin P. Multi-dimensional gated recurrent units for the segmentation of biomedical 3D-data. Cham: Springer International Publishing; 2016. p. 142–51.

    Google Scholar 

  30. Li H, Jiang G, Zhang J, Wang R, Wang Z, Zheng WS, et al. Fully convolutional network ensembles for white matter hyperintensities segmentation in MR images. Neuroimage. 2018;183:650–65.

    Article  Google Scholar 

Download references

Acknowledgements

This work was supported by the Basic Science Research Program through the National Research Foundation of Korea and the Bio & Medical Technology Development Program of the National Research Foundation of Korea funded by the Ministry of Science and ICT (NRF-2018M3C7A1056898 and NRF-2018M3A9H6081483).

Author information

Authors and Affiliations

  1. Department of Medical Engineering, Yonsei University College of Medicine, Seoul, Republic of Korea

    Kyeong Taek Oh & Sun Kook Yoo

  2. Department of Nuclear Medicine, Yonsei University College of Medicine, Seoul, Republic of Korea

    Dongwoo Kim, Sangwon Lee & Mijin Yun

  3. Department of Neurology, Yonsei University College of Medicine, Seoul, Republic of Korea

    Byoung Seok Ye

Authors
  1. Kyeong Taek Oh
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Dongwoo Kim
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Byoung Seok Ye
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Sangwon Lee
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Mijin Yun
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Sun Kook Yoo
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Mijin Yun or Sun Kook Yoo.

Ethics declarations

Ethics approval and consent to participate

All procedures performed in the studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and with the 1964 Helsinki Declaration and its later amendments or comparable ethical standards. This article does not contain any studies with animals performed by any of the authors. Informed consent was obtained from all individual participants in the study.

Conflict of interest

The authors declare no competing interests.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

This article is part of the Topical Collection on Advanced Image Analyses (Radiomics and Artificial Intelligence)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Oh, K.T., Kim, D., Ye, B.S. et al. Segmentation of white matter hyperintensities on 18F-FDG PET/CT images with a generative adversarial network. Eur J Nucl Med Mol Imaging 48, 3422–3431 (2021). https://doi.org/10.1007/s00259-021-05285-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00259-021-05285-4

Keywords

Search

Navigation